Spatio temporal feature evaluation for action recognition

Spatio-Temporal interest points are the most popular feature representation in the field of action recognition. A variety of methods have been proposed to detect and describe local patches in video with several techniques reporting state of the art performance for action recognition. However, the reported results are obtained under different experimental settings with different datasets, making it difficult to compare the various approaches. As a result of this, we seek to comprehensively evaluate state of the art spatio- temporal features under a common evaluation framework with popular benchmark datasets (KTH, Weizmann) and more challenging datasets such as Hollywood2. The purpose of this work is to provide guidance for researchers, when selecting features for different applications with different environmental conditions. In this work we evaluate four popular descriptors (HOG, HOF, HOG/HOF, HOG3D) using a popular bag of visual features representation, and Support Vector Machines (SVM)for classification. Moreover, we provide an in-depth analysis of local feature descriptors and optimize the codebook sizes for different datasets with different descriptors. In this paper, we demonstrate that motion based features offer better performance than those that rely solely on spatial information, while features that combine both types of data are more consistent across a variety of conditions, but typically require a larger codebook for optimal performance.

Library research support in Queensland : a survey

University libraries worldwide are reconceptualising the ways in which they support the research agenda in their respective institutions. This paper is based on a survey completed by member libraries of the Queensland University Libraries Office of Cooperation (QUL OC), the findings of which may be informative for other university libraries. After briefly examining major emerging trends in research support, the paper discusses the results of the survey specifically focussing on support for researchers and the research agenda in their institutions. All responding libraries offer a high level of research support, however, eResearch support, in general, and research data management support, in particular, have the highest variance among the libraries, and signal possible areas for growth. Areas for follow-up, benchmarking and development are suggested.

Supplementary Information : Hogan, Holland, Holloway, Petit and Read : Read Classification for Next Generation Sequencing, ESANN 2013, April 2013

This item provides supplementary materials for the paper mentioned in the title, specifically a range of organisms used in the study. The full abstract for the main paper is as follows: Next Generation Sequencing (NGS) technologies have revolutionised molecular biology, allowing clinical sequencing to become a matter of routine. NGS data sets consist of short sequence reads obtained from the machine, given context and meaning through downstream assembly and annotation. For these techniques to operate successfully, the collected reads must be consistent with the assumed species or species group, and not corrupted in some way. The common bacterium Staphylococcus aureus may cause severe and life-threatening infections in humans,with some strains exhibiting antibiotic resistance. In this paper, we apply an SVM classifier to the important problem of distinguishing S. aureus sequencing projects from alternative pathogens, including closely related Staphylococci. Using a sequence k-mer representation, we achieve precision and recall above 95%, implicating features with important functional associations.

V1-inspired features induce a weighted margin in SVMs

Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good performance in a myriad of visual classification tasks including object recognition/detection, pedestrian detection and facial expression classification. A central question in the vision, learning and neuroscience communities regards why these architectures perform so well. In this paper, we offer a unique perspective to this question by subsuming the role of V1-inspired features directly within a linear support vector machine (SVM). We demonstrate that a specific class of such features in conjunction with a linear SVM can be reinterpreted as inducing a weighted margin on the Kronecker basis expansion of an image. This new viewpoint on the role of V1-inspired features allows us to answer fundamental questions on the uniqueness and redundancies of these features, and offer substantial improvements in terms of computational and storage efficiency.

Inferencing design styles using Baysian Networks

Reasoning with uncertain knowledge and belief has long been recognized as an important research issue in Artificial Intelligence (AI). Several methodologies have been proposed in the past, including knowledge-based systems, fuzzy sets, and probability theory. The probabilistic approach became popular mainly due to a knowledge representation framework called Bayesian networks. Bayesian networks have earned reputation of being powerful tools for modeling complex problem involving uncertain knowledge. Uncertain knowledge exists in domains such as medicine, law, geographical information systems and design as it is difficult to retrieve all knowledge and experience from experts. In design domain, experts believe that design style is an intangible concept and that its knowledge is difficult to be presented in a formal way. The aim of the research is to find ways to represent design style knowledge in Bayesian net works. We showed that these networks can be used for diagnosis (inferences) and classification of design style. The furniture design style is selected as an example domain, however the method can be used for any other domain.

In situ SANS study of the surface and pore filling adsorption of subcritical and supercritical CO2 in porous silica as a function of pore size

We applied small-angle neutron scattering (SANS) and ultra small-angle neutron scattering (USANS) to monitor evolution of the CO2 adsorption in porous silica as a function of CO2 pressure and temperature in pores of different sizes. The range of pressures (0 < P < 345 bar) and temperatures (T=18 OC, 35 OC and 60 OC) corresponded to subcritical, near critical and supercritical conditions of bulk fluid. We observed that the adsorption behavior of CO2 is fundamentally different in large and small pores with the sizes D > 100 Å and D < 30 Å, respectively. Scattering data from large pores indicate formation of a dense adsorbed film of CO2 on pore walls with the liquid-like density (ρCO2)ads≈0.8 g/cm3. The adsorbed film coexists with unadsorbed fluid in the inner pore volume. The density of unadsorbed fluid in large pores is temperature and pressure dependent: it is initially lower than (ρCO2)ads and gradually approaches it with pressure. In small pores compressed CO2 gas completely fills the pore volume. At the lowest pressures of the order of 10 bar and T=18 OC, the fluid density in smallest pores available in the matrix with D ~ 10 Å exceeds bulk fluid density by a factor of ~ 8. As pressure increases, progressively larger pores become filled with the condensed CO2. Fluid densification is only observed in pores with sizes less than ~ 25 – 30 Å. As the density of the invading fluid reaches (ρCO2)bulk~ 0.8 g/cm3, pores of all sizes become uniformly filled with CO2 and the confinement effects disappear. At higher densities the fluid in small pores appears to follow the equation of state of bulk CO2 although there is an indication that the fluid density in the inner volume of large pores may exceed the density of the adsorbed layer. The equivalent internal pressure (Pint) in the smallest pores exceeds the external pressure (Pext) by a factor of ~ 5 for both sub- and supercritical CO2. Pint gradually approaches Pext as D → 25 – 30 Å and is independent of temperature in the studied range of 18 OC ≤ T ≤ 60 OC. The obtained results demonstrate certain similarity as well as differences between adsorption of subcritical and supercritical CO2 in disordered porous silica. High pressure small angle scattering experiments open new opportunities for in situ studies of the fluid adsorption in porous media of interest to CO2 sequestration, energy storage, and heterogeneous catalysis.

Effect of rehydration on structure and surface properties of thermally treated palygorskite

Palygorskite has a fibrous like morphology with a distinctive layered appearance. The simplified formula of palygorskite (Mg5Si8O20(OH)2(OH2)4 nH2O) indicates that two different types of water are present. The dehydration and rehydration of palygorskite have been studied using thermogravimetry and H2O-tem- perature programmed desorption. X-ray diffractograms, NH3 adsorption profiles, and NH3 desorption profiles were obtained for thermally treated palygorskite as a function of temperature. The results proved water molecules were mainly derived from Si–OH units. In addition, five kinds of acid sites were found for palygorskite. The number of acid sites of external surfaces was larger than that of the internal sur- faces. Bonding on the internal surface acid sites was stronger than the bonding of the external surfaces. Rehydration restored the folded structure of palygorskite when thermal treatment temperature was lower than 300 oC.

Bearing fault prognosis based on health state probability estimation

In condition-based maintenance (CBM), effective diagnostic and prognostic tools are essential for maintenance engineers to identify imminent fault and predict the remaining useful life before the components finally fail. This enables remedial actions to be taken in advance and reschedule of production if necessary. All machine components are subjected to degradation processes in real environments and they have certain failure characteristics which can be related to the operating conditions. This paper describes a technique for accurate assessment of the remnant life of bearings based on health state probability estimation and historical knowledge embedded in the closed loop diagnostics and prognostics system. The technique uses the Support Vector Machine (SVM) classifier as a tool for estimating health state probability of machine degradation process to provide long term prediction. To validate the feasibility of the proposed model, real life fault historical data from bearings of High Pressure-Liquefied Natural Gas (HP-LNG) pumps were analysed and used to obtain the optimal prediction of remaining useful life (RUL). The results obtained were very encouraging and showed that the proposed prognosis system based on health state probability estimation has the potential to be used as an estimation tool for remnant life prediction in industrial machinery.

Examining the influence of participant performance factors on contractor satisfaction : a structural equation model

Participant performance is critical to the success of projects. At the same time, enhancing the satisfaction of participants not only helps in problem solving but also improves their motivation and cooperation. However, previous research related to participant satisfaction is primarily concerned with clients and customers and relatively little attention has been paid to contractors. This paper investigates how the performance of project participants affects contractor project satisfaction in terms of the client's clarity of objectives (OC) and promptness of payments (PP), designer carefulness (DC), construction risk management (RM), the effectiveness their contribution (EW) and mutual respect and trust (RT). With 125 valid responses from contractors in Malaysia, a contractor satisfaction model is developed based on structural equation modelling. The results demonstrate the necessity for dividing abstract satisfaction into two dimensions, comprising economic-related satisfaction (ES) and production-related satisfaction (PS), with DC, OC, PP and RM having significant effects on ES, while DC, OC, EW and RM influence PS. In addition, the model tests the indirect effects of these performance variables on ES and PS. In particular, OC indirectly affects ES and PS through mediation of RM and DC respectively. The results also provide opportunities for improving contractor satisfaction and supplementing the contractor selection criteria for clients.

Read classification for next generation sequencing

Next Generation Sequencing (NGS) has revolutionised molec- ular biology, allowing routine clinical sequencing. NGS data consists of short sequence reads, given context through downstream assembly and annotation, a process requiring reads consistent with the assumed species or species group. The common bacterium Staphylococcus aureus may cause severe and life-threatening infections in humans, with some strains exhibiting antibiotic resistance. Here we apply an SVM classifier to the important problem of distinguishing S. aureus sequencing projects from other pathogens, including closely related Staphylococci. Using a sequence k-mer representation, we achieve precision and recall above 95%, implicating features with important functional associations.

The impact of organisational culture in project selection process : case of public infrastructure project in Indonesia

The thesis develops an Organisational Culture (OC) based framework for potentially improving the current practice of the infrastructure project selection process (PSP) in Indonesia, particularly for regional road projects. This framework is developed to address the suggestion emanating from the research that there is a need for strengthening the relevant organisational culture dimensions and making changes to current organisational culture profiles to support the effectiveness of the decision-making process of the current PSP. The findings not only benefit existing knowledge but also provide practical contributions for those decision-makers within the Indonesian regional government that are involved in PSP, i.e. by raising the awareness of the influence and the role of organisational culture.

Semi-binary based video features for activity representation

Efficient and effective feature detection and representation is an important consideration when processing videos, and a large number of applications such as motion analysis, 3D scene understanding, tracking etc. depend on this. Amongst several feature description methods, local features are becoming increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational complexity, their performance is still too limited for real world applications. Furthermore, rapid increases in the uptake of mobile devices has increased the demand for algorithms that can run with reduced memory and computational requirements. In this paper we propose a semi binary based feature detectordescriptor based on the BRISK detector, which can detect and represent videos with significantly reduced computational requirements, while achieving comparable performance to the state of the art spatio-temporal feature descriptors. First, the BRISK feature detector is applied on a frame by frame basis to detect interest points, then the detected key points are compared against consecutive frames for significant motion. Key points with significant motion are encoded with the BRISK descriptor in the spatial domain and Motion Boundary Histogram in the temporal domain. This descriptor is not only lightweight but also has lower memory requirements because of the binary nature of the BRISK descriptor, allowing the possibility of applications using hand held devices.We evaluate the combination of detectordescriptor performance in the context of action classification with a standard, popular bag-of-features with SVM framework. Experiments are carried out on two popular datasets with varying complexity and we demonstrate comparable performance with other descriptors with reduced computational complexity.

Predicting fault-prone software modules with rank sum classification

The detection and correction of defects remains among the most time consuming and expensive aspects of software development. Extensive automated testing and code inspections may mitigate their effect, but some code fragments are necessarily more likely to be faulty than others, and automated identification of fault prone modules helps to focus testing and inspections, thus limiting wasted effort and potentially improving detection rates. However, software metrics data is often extremely noisy, with enormous imbalances in the size of the positive and negative classes. In this work, we present a new approach to predictive modelling of fault proneness in software modules, introducing a new feature representation to overcome some of these issues. This rank sum representation offers improved or at worst comparable performance to earlier approaches for standard data sets, and readily allows the user to choose an appropriate trade-off between precision and recall to optimise inspection effort to suit different testing environments. The method is evaluated using the NASA Metrics Data Program (MDP) data sets, and performance is compared with existing studies based on the Support Vector Machine (SVM) and Naïve Bayes (NB) Classifiers, and with our own comprehensive evaluation of these methods.

Prediction of CO concentrations based on a hybrid Partial Least Square and Support Vector Machine model

Due to the health impacts caused by exposures to air pollutants in urban areas, monitoring and forecasting of air quality parameters have become popular as an important topic in atmospheric and environmental research today. The knowledge on the dynamics and complexity of air pollutants behavior has made artificial intelligence models as a useful tool for a more accurate pollutant concentration prediction. This paper focuses on an innovative method of daily air pollution prediction using combination of Support Vector Machine (SVM) as predictor and Partial Least Square (PLS) as a data selection tool based on the measured values of CO concentrations. The CO concentrations of Rey monitoring station in the south of Tehran, from Jan. 2007 to Feb. 2011, have been used to test the effectiveness of this method. The hourly CO concentrations have been predicted using the SVM and the hybrid PLS–SVM models. Similarly, daily CO concentrations have been predicted based on the aforementioned four years measured data. Results demonstrated that both models have good prediction ability; however the hybrid PLS–SVM has better accuracy. In the analysis presented in this paper, statistic estimators including relative mean errors, root mean squared errors and the mean absolute relative error have been employed to compare performances of the models. It has been concluded that the errors decrease after size reduction and coefficients of determination increase from 56 to 81% for SVM model to 65–85% for hybrid PLS–SVM model respectively. Also it was found that the hybrid PLS–SVM model required lower computational time than SVM model as expected, hence supporting the more accurate and faster prediction ability of hybrid PLS–SVM model.

Supplementary material : large scale read classification for next generation sequencing

Next Generation Sequencing (NGS) has revolutionised molecular biology, resulting in an explosion of data sets and an increasing role in clinical practice. Such applications necessarily require rapid identification of the organism as a prelude to annotation and further analysis. NGS data consist of a substantial number of short sequence reads, given context through downstream assembly and annotation, a process requiring reads consistent with the assumed species or species group. Highly accurate results have been obtained for restricted sets using SVM classifiers, but such methods are difficult to parallelise and success depends on careful attention to feature selection. This work examines the problem at very large scale, using a mix of synthetic and real data with a view to determining the overall structure of the problem and the effectiveness of parallel ensembles of simpler classifiers (principally random forests) in addressing the challenges of large scale genomics.